English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

crucial for transportation management. However, traditional spatial-temporaldeep learning models grapple with addressing the sparse and long-tailcharacteristics in high-resolution O-D matrices and quantifying predictionuncertainty. This dilemma arises from the numerous zeros and over-disperseddemand patterns within these matrices, which challenge the Gaussian assumptioninherent to deterministic deep learning models. To address these challenges, wepropose a novel approach: the Spatial-Temporal Tweedie Graph Neural Network(STTD). The STTD introduces the Tweedie distribution as a compellingalternative to the traditional 'zero-inflated' model and leverages spatial andtemporal embeddings to parameterize travel demand distributions. Ourevaluations using real-world datasets highlight STTD's superiority in providingaccurate predictions and precise confidence intervals, particularly inhigh-resolution scenarios.

Uncertainty Quantification via Spatial-Temporal Tweedie Model for Zero-inflated and Long-tail Travel Demand Prediction